Skip to content

pydvl.influence.base_influence_function_model

ComposableInfluence

Bases: InfluenceFunctionModel, Generic[TensorType, BatchType, DataLoaderType, BlockMapperType], ABC

Generic abstract base class, that allow for block-wise computation of influence quantities. Inherit from this base class for specific influence algorithms and tensor frameworks.

is_thread_safe abstractmethod property 

is_thread_safe: bool

Whether the influence computation is thread safe

n_parameters abstractmethod property 

n_parameters

Number of trainable parameters of the underlying model

_concat abstractmethod 

_concat(tensors: Iterable[TensorType], dim: int)

Implement this to concat tensors at a specified dimension

Source code in src/pydvl/influence/base_influence_function_model.py 
425
426
427
@abstractmethod
def _concat(self, tensors: Iterable[TensorType], dim: int):
    """Implement this to concat tensors at a specified dimension"""

_create_batch abstractmethod staticmethod 

_create_batch(x: TensorType, y: TensorType) -> BatchType

Implement this method to provide the creation of a subtype of Batch for a specific framework

Source code in src/pydvl/influence/base_influence_function_model.py 
503
504
505
506
507
508
@staticmethod
@abstractmethod
def _create_batch(x: TensorType, y: TensorType) -> BatchType:
    """Implement this method to provide the creation of a subtype of
    [Batch][pydvl.influence.types.Batch] for a specific framework
    """

_create_block_mapper abstractmethod 

_create_block_mapper(data: DataLoaderType) -> BlockMapperType

Override this method to create a block mapper instance, that can be used to compute block-wise influence quantities.

PARAMETER DESCRIPTION
data

iterable of tensors

TYPE: DataLoaderType

RETURNS DESCRIPTION
BlockMapperType

BlockMapper instance
Source code in src/pydvl/influence/base_influence_function_model.py 
278
279
280
281
282
283
284
285
286
287
288
289
290
@abstractmethod
def _create_block_mapper(self, data: DataLoaderType) -> BlockMapperType:
    """
    Override this method to create a block mapper instance, that can be used
    to compute block-wise influence quantities.

    Args:
        data: iterable of tensors

    Returns:
        BlockMapper instance
    """
    pass

_flatten_trailing_dim abstractmethod 

_flatten_trailing_dim(tensor: TensorType)

Implement this to flatten all but the first dimension

Source code in src/pydvl/influence/base_influence_function_model.py 
429
430
431
@abstractmethod
def _flatten_trailing_dim(self, tensor: TensorType):
    """Implement this to flatten all but the first dimension"""

fit 

fit(data: DataLoaderType) -> InfluenceFunctionModel

Fitting to provided data, by internally creating a block mapper instance from it. Args: data: iterable of tensors

RETURNS DESCRIPTION
InfluenceFunctionModel

Fitted instance
Source code in src/pydvl/influence/base_influence_function_model.py 
264
265
266
267
268
269
270
271
272
273
274
275
276
@log_duration(log_level=logging.INFO)
def fit(self, data: DataLoaderType) -> InfluenceFunctionModel:
    """
    Fitting to provided data, by internally creating a block mapper instance from
    it.
    Args:
        data: iterable of tensors

    Returns:
        Fitted instance
    """
    self.block_mapper = self._create_block_mapper(data)
    return self

fit_required staticmethod 

fit_required(method)

Decorator to enforce the fitted check

Source code in src/pydvl/influence/base_influence_function_model.py 
59
60
61
62
63
64
65
66
67
68
69
@staticmethod
def fit_required(method):
    """Decorator to enforce the fitted check"""

    @wraps(method)
    def wrapper(self, *args, **kwargs):
        if not self.is_fitted:
            raise NotFittedException(type(self))
        return method(self, *args, **kwargs)

    return wrapper

influence_factors 

influence_factors(x: TensorType, y: TensorType) -> TensorType

Computes the approximation of

\[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

where the gradient is meant to be per sample of the batch \((x, y)\). For all input tensors it is assumed, that the first dimension is the batch dimension.

PARAMETER DESCRIPTION
x

model input to use in the gradient computations

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise inverse Hessian matrix vector products
Source code in src/pydvl/influence/base_influence_function_model.py 
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
def influence_factors(self, x: TensorType, y: TensorType) -> TensorType:
    r"""
    Computes the approximation of

    \[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

    where the gradient is meant to be per sample of the batch $(x, y)$.
    For all input tensors it is assumed,
    that the first dimension is the batch dimension.

    Args:
        x: model input to use in the gradient computations
        y: label tensor to compute gradients

    Returns:
        Tensor representing the element-wise inverse Hessian matrix vector products

    """
    if not self.is_fitted:
        raise NotFittedException(type(self))
    return self._influence_factors(x, y)

influence_factors_by_block 

influence_factors_by_block(
    x: TensorType, y: TensorType
) -> OrderedDict[str, TensorType]

Compute the block-wise approximation of

\[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

where the gradient is meant to be per sample of the batch \((x, y)\).

PARAMETER DESCRIPTION
x

model input to use in the gradient computations

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

RETURNS DESCRIPTION
OrderedDict[str, TensorType]

Ordered dictionary of tensors representing the element-wise
OrderedDict[str, TensorType]

approximate inverse Hessian matrix vector products per block.
Source code in src/pydvl/influence/base_influence_function_model.py 
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
@InfluenceFunctionModel.fit_required
def influence_factors_by_block(
    self, x: TensorType, y: TensorType
) -> OrderedDict[str, TensorType]:
    r"""
    Compute the block-wise approximation of

    \[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

    where the gradient is meant to be per sample of the batch $(x, y)$.

    Args:
        x: model input to use in the gradient computations
        y: label tensor to compute gradients

    Returns:
        Ordered dictionary of tensors representing the element-wise
        approximate inverse Hessian matrix vector products per block.

    """
    return self.block_mapper.transformed_grads(self._create_batch(x, y))

influences 

influences(
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = Up,
) -> TensorType

Computes the approximation of

\[ \langle H^{-1}\nabla_{\theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}})), \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle H^{-1}\nabla_{\theta} \ell(y_{test}, f_{\theta}(x_{test})), \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case.

PARAMETER DESCRIPTION
x_test

model input to use in the gradient computations of \(H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))\)

TYPE: TensorType

y_test

label tensor to compute gradients

TYPE: TensorType

x

optional model input to use in the gradient computations \(\nabla_{theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{test}\)

TYPE: Optional[TensorType] DEFAULT: None

y

optional label tensor to compute gradients

TYPE: Optional[TensorType] DEFAULT: None

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise scalar products for the provided batch
Source code in src/pydvl/influence/base_influence_function_model.py 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
def influences(
    self,
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = InfluenceMode.Up,
) -> TensorType:
    r"""
    Computes the approximation of

    \[ \langle H^{-1}\nabla_{\theta} \ell(y_{\text{test}},
        f_{\theta}(x_{\text{test}})),
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle H^{-1}\nabla_{\theta} \ell(y_{test}, f_{\theta}(x_{test})),
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case.

    Args:
        x_test: model input to use in the gradient computations
            of $H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))$
        y_test: label tensor to compute gradients
        x: optional model input to use in the gradient computations
            $\nabla_{theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{test}$
        y: optional label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Tensor representing the element-wise scalar products for the provided batch

    """
    if not self.is_fitted:
        raise NotFittedException(type(self))

    if x is None and y is not None:
        raise ValueError(
            "Providing labels y, without providing model input x is not supported"
        )

    if x is not None and y is None:
        raise ValueError(
            "Providing model input x, without providing labels y is not supported"
        )

    return self._influences(x_test, y_test, x, y, mode)

influences_by_block 

influences_by_block(
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = Up,
) -> OrderedDict[str, TensorType]

Compute the block-wise influence values for the provided data, i.e. an approximation of

\[ \langle H^{-1}\nabla_{theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}})), \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test})), \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case.

PARAMETER DESCRIPTION
x_test

model input to use in the gradient computations of the approximation of \(H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))\)

TYPE: TensorType

y_test

label tensor to compute gradients

TYPE: TensorType

x

optional model input to use in the gradient computations \(\nabla_{theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{test}\)

TYPE: Optional[TensorType] DEFAULT: None

y

optional label tensor to compute gradients

TYPE: Optional[TensorType] DEFAULT: None

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
OrderedDict[str, TensorType]

Ordered dictionary of tensors representing the element-wise scalar products
OrderedDict[str, TensorType]

for the provided batch per block.
Source code in src/pydvl/influence/base_influence_function_model.py 
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
@InfluenceFunctionModel.fit_required
def influences_by_block(
    self,
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = InfluenceMode.Up,
) -> OrderedDict[str, TensorType]:
    r"""
    Compute the block-wise influence values for the provided data, i.e. an
    approximation of

    \[ \langle H^{-1}\nabla_{theta} \ell(y_{\text{test}},
        f_{\theta}(x_{\text{test}})),
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test})),
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case.

    Args:
        x_test: model input to use in the gradient computations
            of the approximation of
            $H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))$
        y_test: label tensor to compute gradients
        x: optional model input to use in the gradient computations
            $\nabla_{theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{test}$
        y: optional label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Ordered dictionary of tensors representing the element-wise scalar products
        for the provided batch per block.

    """
    left_batch = self._create_batch(x_test, y_test)

    if x is None:
        if y is not None:
            raise ValueError(
                "Providing labels y, without providing model input x "
                "is not supported"
            )
        right_batch = left_batch
    else:
        if y is None:
            raise ValueError(
                "Providing model input x, without providing labels y "
                "is not supported"
            )
        right_batch = self._create_batch(x, y)

    return self.block_mapper.interactions(left_batch, right_batch, mode)

influences_from_factors 

influences_from_factors(
    z_test_factors: TensorType,
    x: TensorType,
    y: TensorType,
    mode: InfluenceMode = Up,
) -> TensorType

Computation of

\[ \langle z_{\text{test_factors}}, \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle z_{\text{test_factors}}, \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case. The gradient is meant to be per sample of the batch \((x, y)\).

PARAMETER DESCRIPTION
z_test_factors

pre-computed array, approximating \(H^{-1}\nabla_{\theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}}))\)

TYPE: TensorType

x

model input to use in the gradient computations \(\nabla_{\theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{\theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{\text{test}}\)

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise scalar products for the provided batch
Source code in src/pydvl/influence/base_influence_function_model.py 
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
@InfluenceFunctionModel.fit_required
def influences_from_factors(
    self,
    z_test_factors: TensorType,
    x: TensorType,
    y: TensorType,
    mode: InfluenceMode = InfluenceMode.Up,
) -> TensorType:
    r"""
    Computation of

    \[ \langle z_{\text{test_factors}},
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle z_{\text{test_factors}},
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case. The gradient is meant to be per sample
    of the batch $(x, y)$.

    Args:
        z_test_factors: pre-computed array, approximating
            $H^{-1}\nabla_{\theta} \ell(y_{\text{test}},
            f_{\theta}(x_{\text{test}}))$
        x: model input to use in the gradient computations
            $\nabla_{\theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{\theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{\text{test}}$
        y: label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Tensor representing the element-wise scalar products for the provided batch

    """
    tensors = self.block_mapper.generate_interactions_from_transformed_grads(
        z_test_factors,
        self._create_batch(x, y),
        mode,
    )
    result: TensorType = next(tensors)
    for tensor in tensors:
        result = result + tensor
    return result

influences_from_factors_by_block 

influences_from_factors_by_block(
    z_test_factors: OrderedDict[str, TensorType],
    x: TensorType,
    y: TensorType,
    mode: InfluenceMode = Up,
) -> OrderedDict[str, TensorType]

Block-wise computation of

\[ \langle z_{\text{test_factors}}, \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle z_{\text{test_factors}}, \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case. The gradient is meant to be per sample of the batch \((x, y)\).

PARAMETER DESCRIPTION
z_test_factors

pre-computed array, approximating \(H^{-1}\nabla_{\theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}}))\)

TYPE: OrderedDict[str, TensorType]

x

model input to use in the gradient computations \(\nabla_{\theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{\theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{\text{test}}\)

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
OrderedDict[str, TensorType]

Ordered dictionary of tensors representing the element-wise scalar products
OrderedDict[str, TensorType]

for the provided batch per block
Source code in src/pydvl/influence/base_influence_function_model.py 
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
@InfluenceFunctionModel.fit_required
def influences_from_factors_by_block(
    self,
    z_test_factors: OrderedDict[str, TensorType],
    x: TensorType,
    y: TensorType,
    mode: InfluenceMode = InfluenceMode.Up,
) -> OrderedDict[str, TensorType]:
    r"""
    Block-wise computation of

    \[ \langle z_{\text{test_factors}},
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle z_{\text{test_factors}},
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case. The gradient is meant to be per sample
    of the batch $(x, y)$.

    Args:
        z_test_factors: pre-computed array, approximating
            $H^{-1}\nabla_{\theta} \ell(y_{\text{test}},
            f_{\theta}(x_{\text{test}}))$
        x: model input to use in the gradient computations
            $\nabla_{\theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{\theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{\text{test}}$
        y: label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Ordered dictionary of tensors representing the element-wise scalar products
        for the provided batch per block

    """
    return self.block_mapper.interactions_from_transformed_grads(
        z_test_factors, self._create_batch(x, y), mode
    )

InfluenceFunctionModel

Bases: Generic[TensorType, DataLoaderType], ABC

Generic abstract base class for computing influence related quantities. For a specific influence algorithm and tensor framework, inherit from this base class

is_fitted abstractmethod property 

is_fitted

Override this, to expose the fitting status of the instance.

is_thread_safe abstractmethod property 

is_thread_safe: bool

Whether the influence computation is thread safe

n_parameters abstractmethod property 

n_parameters

Number of trainable parameters of the underlying model

_influence_factors abstractmethod 

_influence_factors(x: TensorType, y: TensorType) -> TensorType

Override this method to implement the approximation of

\[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

where the gradient is meant to be per sample of the batch \((x, y)\).

PARAMETER DESCRIPTION
x

model input to use in the gradient computations

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise inverse Hessian matrix vector products
Source code in src/pydvl/influence/base_influence_function_model.py 
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
@abstractmethod
def _influence_factors(self, x: TensorType, y: TensorType) -> TensorType:
    r"""
    Override this method to implement the approximation of

    \[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

    where the gradient is meant to be per sample of the batch $(x, y)$.

    Args:
        x: model input to use in the gradient computations
        y: label tensor to compute gradients

    Returns:
        Tensor representing the element-wise inverse Hessian matrix vector products

    """

_influences abstractmethod 

_influences(
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = Up,
) -> TensorType

Override this method to implement the approximation of

\[ \langle H^{-1}\nabla_{theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}})), \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test})), \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case.

PARAMETER DESCRIPTION
x_test

model input to use in the gradient computations of \(H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))\)

TYPE: TensorType

y_test

label tensor to compute gradients

TYPE: TensorType

x

optional model input to use in the gradient computations \(\nabla_{theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{test}\)

TYPE: Optional[TensorType] DEFAULT: None

y

optional label tensor to compute gradients

TYPE: Optional[TensorType] DEFAULT: None

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise scalar products for the provided batch
Source code in src/pydvl/influence/base_influence_function_model.py 
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
@abstractmethod
def _influences(
    self,
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = InfluenceMode.Up,
) -> TensorType:
    r"""
    Override this method to implement the approximation of

    \[ \langle H^{-1}\nabla_{theta} \ell(y_{\text{test}},
        f_{\theta}(x_{\text{test}})),
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test})),
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case.

    Args:
        x_test: model input to use in the gradient computations
            of $H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))$
        y_test: label tensor to compute gradients
        x: optional model input to use in the gradient computations
            $\nabla_{theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{test}$
        y: optional label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Tensor representing the element-wise scalar products for the provided batch

    """

fit abstractmethod 

fit(data: DataLoaderType) -> InfluenceFunctionModel

Override this method to fit the influence function model to training data, e.g. pre-compute hessian matrix or matrix decompositions

PARAMETER DESCRIPTION
data

TYPE: DataLoaderType

RETURNS DESCRIPTION
InfluenceFunctionModel

The fitted instance
Source code in src/pydvl/influence/base_influence_function_model.py 
46
47
48
49
50
51
52
53
54
55
56
57
@abstractmethod
def fit(self, data: DataLoaderType) -> InfluenceFunctionModel:
    """
    Override this method to fit the influence function model to training data,
    e.g. pre-compute hessian matrix or matrix decompositions

    Args:
        data:

    Returns:
        The fitted instance
    """

fit_required staticmethod 

fit_required(method)

Decorator to enforce the fitted check

Source code in src/pydvl/influence/base_influence_function_model.py 
59
60
61
62
63
64
65
66
67
68
69
@staticmethod
def fit_required(method):
    """Decorator to enforce the fitted check"""

    @wraps(method)
    def wrapper(self, *args, **kwargs):
        if not self.is_fitted:
            raise NotFittedException(type(self))
        return method(self, *args, **kwargs)

    return wrapper

influence_factors 

influence_factors(x: TensorType, y: TensorType) -> TensorType

Computes the approximation of

\[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

where the gradient is meant to be per sample of the batch \((x, y)\). For all input tensors it is assumed, that the first dimension is the batch dimension.

PARAMETER DESCRIPTION
x

model input to use in the gradient computations

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise inverse Hessian matrix vector products
Source code in src/pydvl/influence/base_influence_function_model.py 
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
def influence_factors(self, x: TensorType, y: TensorType) -> TensorType:
    r"""
    Computes the approximation of

    \[ H^{-1}\nabla_{\theta} \ell(y, f_{\theta}(x)) \]

    where the gradient is meant to be per sample of the batch $(x, y)$.
    For all input tensors it is assumed,
    that the first dimension is the batch dimension.

    Args:
        x: model input to use in the gradient computations
        y: label tensor to compute gradients

    Returns:
        Tensor representing the element-wise inverse Hessian matrix vector products

    """
    if not self.is_fitted:
        raise NotFittedException(type(self))
    return self._influence_factors(x, y)

influences 

influences(
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = Up,
) -> TensorType

Computes the approximation of

\[ \langle H^{-1}\nabla_{\theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}})), \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle H^{-1}\nabla_{\theta} \ell(y_{test}, f_{\theta}(x_{test})), \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case.

PARAMETER DESCRIPTION
x_test

model input to use in the gradient computations of \(H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))\)

TYPE: TensorType

y_test

label tensor to compute gradients

TYPE: TensorType

x

optional model input to use in the gradient computations \(\nabla_{theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{test}\)

TYPE: Optional[TensorType] DEFAULT: None

y

optional label tensor to compute gradients

TYPE: Optional[TensorType] DEFAULT: None

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise scalar products for the provided batch
Source code in src/pydvl/influence/base_influence_function_model.py 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
def influences(
    self,
    x_test: TensorType,
    y_test: TensorType,
    x: Optional[TensorType] = None,
    y: Optional[TensorType] = None,
    mode: InfluenceMode = InfluenceMode.Up,
) -> TensorType:
    r"""
    Computes the approximation of

    \[ \langle H^{-1}\nabla_{\theta} \ell(y_{\text{test}},
        f_{\theta}(x_{\text{test}})),
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle H^{-1}\nabla_{\theta} \ell(y_{test}, f_{\theta}(x_{test})),
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case.

    Args:
        x_test: model input to use in the gradient computations
            of $H^{-1}\nabla_{theta} \ell(y_{test}, f_{\theta}(x_{test}))$
        y_test: label tensor to compute gradients
        x: optional model input to use in the gradient computations
            $\nabla_{theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{test}$
        y: optional label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Tensor representing the element-wise scalar products for the provided batch

    """
    if not self.is_fitted:
        raise NotFittedException(type(self))

    if x is None and y is not None:
        raise ValueError(
            "Providing labels y, without providing model input x is not supported"
        )

    if x is not None and y is None:
        raise ValueError(
            "Providing model input x, without providing labels y is not supported"
        )

    return self._influences(x_test, y_test, x, y, mode)

influences_from_factors abstractmethod 

influences_from_factors(
    z_test_factors: TensorType,
    x: TensorType,
    y: TensorType,
    mode: InfluenceMode = Up,
) -> TensorType

Override this method to implement the computation of

\[ \langle z_{\text{test_factors}}, \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the case of up-weighting influence, resp.

\[ \langle z_{\text{test_factors}}, \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

for the perturbation type influence case. The gradient is meant to be per sample of the batch \((x, y)\).

PARAMETER DESCRIPTION
z_test_factors

pre-computed array, approximating \(H^{-1}\nabla_{\theta} \ell(y_{\text{test}}, f_{\theta}(x_{\text{test}}))\)

TYPE: TensorType

x

model input to use in the gradient computations \(\nabla_{\theta}\ell(y, f_{\theta}(x))\), resp. \(\nabla_{x}\nabla_{\theta}\ell(y, f_{\theta}(x))\), if None, use \(x=x_{\text{test}}\)

TYPE: TensorType

y

label tensor to compute gradients

TYPE: TensorType

mode

enum value of InfluenceMode

TYPE: InfluenceMode DEFAULT: Up

RETURNS DESCRIPTION
TensorType

Tensor representing the element-wise scalar products for the provided batch
Source code in src/pydvl/influence/base_influence_function_model.py 
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
@abstractmethod
def influences_from_factors(
    self,
    z_test_factors: TensorType,
    x: TensorType,
    y: TensorType,
    mode: InfluenceMode = InfluenceMode.Up,
) -> TensorType:
    r"""
    Override this method to implement the computation of

    \[ \langle z_{\text{test_factors}},
        \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the case of up-weighting influence, resp.

    \[ \langle z_{\text{test_factors}},
        \nabla_{x} \nabla_{\theta} \ell(y, f_{\theta}(x)) \rangle \]

    for the perturbation type influence case. The gradient is meant to be per sample
    of the batch $(x, y)$.

    Args:
        z_test_factors: pre-computed array, approximating
            $H^{-1}\nabla_{\theta} \ell(y_{\text{test}},
            f_{\theta}(x_{\text{test}}))$
        x: model input to use in the gradient computations
            $\nabla_{\theta}\ell(y, f_{\theta}(x))$,
            resp. $\nabla_{x}\nabla_{\theta}\ell(y, f_{\theta}(x))$,
            if None, use $x=x_{\text{test}}$
        y: label tensor to compute gradients
        mode: enum value of [InfluenceMode]
            [pydvl.influence.base_influence_function_model.InfluenceMode]

    Returns:
        Tensor representing the element-wise scalar products for the provided batch

    """